Multi-stage pressure regulating method for natural gas transportation of distributed energy pipelines and Internet of Things system

Abstract

The invention provides a multi-stage pressure regulating method for natural gas transportation of a distributed energy pipeline and an Internet of Things system, the Internet of Things system comprises an operation user platform, an operation service platform, a management platform, a sensing network platform and a sensing control platform, and the pressure regulating method comprises the following steps: determining basic pressurization parameters of a target pressurization station; determining characteristic supercharging parameters of the target supercharging station; generating a pressurization instruction to execute pressurization operation on the natural gas in the downstream pipeline branch; in response to execution of the pressurization instruction, obtaining transportation state data of natural gas in at least one pipeline branch in the preset area; in response to the condition that the transportation state data does not meet the preset condition, linkage adjustment parameters of the target booster station and the associated booster stations are determined; and generating a linkage adjustment instruction based on the linkage adjustment parameter to update the characteristic supercharging parameters of the target supercharging station and the associated supercharging station. According to the method, personalized adjustment of the booster station is facilitated, and therefore it is ensured that the gas pressure of the downstream pipeline branch meets the actual requirement.

Description

Technical Field

[0001] The present invention relates to the field of natural gas transportation, and in particular to a multi-stage pressure regulation method and an Internet of Things system for natural gas transportation in a distributed energy pipeline. Background Art

[0002] The transportation methods of natural gas include pipeline transportation, tank truck transportation and ship transportation. Since most gas fields are concentrated in deserts, polar permafrost zones, mountains, oceans and other areas, the distance from the production site to the use site is often far. Therefore, pipeline transportation has become the most common, economical and reasonable way to transport natural gas over long distances, on a large scale and uninterruptedly. When natural gas is transported through pipelines, the pressure of natural gas will gradually decrease due to the friction between the natural gas and the inner wall of the pipeline and the influence of valves, elbows and other devices, resulting in a decrease in the gas transmission efficiency of the pipeline. Therefore, in the long-distance pipeline branches that transport natural gas, several booster stations are usually set up to avoid the problem of natural gas pressure drop and ensure the smooth transmission of natural gas.

[0003] However, existing booster stations generally use fixed or unified pressure regulation methods. When the types of pipeline branches are different, the environments are different (climate, altitude, height difference between the two ends of the pipeline, etc.), and the transportation specifications or requirements are different, if fixed or unified pressure regulation methods are used for pressure regulation, the pressure of the natural gas in the pipeline branch may be too high or too low, resulting in pipeline branch bursts or insufficient natural gas transportation. In addition, existing booster stations usually lack data interaction with other booster stations, resulting in a lack of coordination between multiple booster stations. In the face of emergency situations, the boosting parameters of multiple booster stations cannot be adjusted in time, resulting in safety hazards.

[0004] Therefore, it is necessary to provide a multi-stage pressure regulation method and Internet of Things system for distributed energy pipeline natural gas transportation, which can personalize the pressure regulation parameters of different booster stations to ensure that natural gas reaches its destination safely and efficiently during long-distance transportation. Summary of the invention

[0005] One or more embodiments of this specification provide a multi-stage pressure regulation method for distributed energy pipeline natural gas transportation. The multi-stage pressure regulation method includes: obtaining the site information of the target boosting station and the downstream pipeline data of the target boosting station from the database of the management platform, and obtaining the boosting task information based on the distributed in-pipe monitoring equipment configured in the upstream pipeline branch in the perception control platform; determining the basic boosting parameters of the target boosting station based on the site information of the target boosting station; determining the characteristic boosting parameters of the target boosting station based on the basic boosting parameters, the downstream pipeline data, and the boosting task information; generating a boosting instruction based on the characteristic boosting parameters and sending it to the target station through the perception control platform. The target boosting station is controlled to perform a boosting operation on the natural gas in the downstream pipeline branch; in response to the boosting instruction being executed, based on the distributed in-pipe monitoring equipment, the transportation status data of the natural gas in at least one pipeline branch in a preset area is obtained; in response to the transportation status data not satisfying a preset condition, the linkage adjustment parameters of the target boosting station and its associated boosting stations are determined based on the transportation status data; based on the linkage adjustment parameters, a linkage adjustment instruction is generated and sent to the perception control platform to update the characteristic boosting parameters of the target boosting station and its associated boosting stations.

[0006] One of the embodiments of this specification provides an Internet of Things system for distributed energy pipeline natural gas transportation, the system comprising an operation user platform, an operation service platform, a management platform, a sensor network platform and a perception control platform that interact in sequence. The management platform is configured to: obtain the site information of the target boosting station and the downstream pipeline data of the downstream pipeline branch of the target boosting station from the database of the management platform, and obtain the boosting task information based on the distributed in-pipe monitoring equipment configured in the upstream pipeline branch in the perception control platform; determine the basic boosting parameters of the target boosting station based on the site information of the target boosting station; determine the characteristic boosting parameters of the target boosting station based on the basic boosting parameters, the downstream pipeline data and the boosting task information; generate a boosting instruction based on the characteristic boosting parameters and send it through the perception control platform The target boosting station is sent to the target boosting station, and the target boosting station is controlled to perform a boosting operation on the natural gas in the downstream pipeline branch; in response to the boosting instruction being executed, based on the distributed in-pipe monitoring equipment, the transportation status data of the natural gas in at least one pipeline branch in a preset area is obtained; in response to the transportation status data not satisfying a preset condition, the linkage adjustment parameters of the target boosting station and its associated boosting stations are determined based on the transportation status data; based on the linkage adjustment parameters, a linkage adjustment instruction is generated and sent to the perception control platform to update the characteristic boosting parameters of the target boosting station and its associated boosting stations.

[0007] The beneficial effects brought by the above invention include but are not limited to: (1) by determining the characteristic boosting parameters of the target boosting station, it is helpful to realize personalized adjustment of the boosting station, so as to ensure that the gas pressure of the downstream pipeline branch of the boosting station meets the actual demand; in response to the transportation status data not meeting the preset conditions, the linkage adjustment parameters of the target boosting station and its associated boosting stations are determined based on the transportation status data, so that when adjusting the boosting parameters of the target boosting station, the potential impact of the natural gas pressure change of the target boosting station on the surrounding boosting stations can be considered, and adaptive adjustments can be made, which is helpful to enhance the synergy between different boosting stations, thereby improving the boosting station management capability of the Internet of Things system and the parallel processing capability of adjusting multiple boosting stations at the same time. (2) based on the correlation influence degree of the pipeline branch, the associated boosting station is determined, which can effectively avoid determining the boosting station corresponding to the pipeline branch less affected by the target boosting station as the associated boosting station, thereby avoiding the waste of computing power and time caused by blindly performing large-scale linkage adjustments, and helping to improve the response speed and computing efficiency of the Internet of Things system for distributed energy pipeline natural gas transportation. (3) By using the pressure consumption model to determine the pressure consumption data of the downstream pipeline branch, the data analysis and computing capabilities of the machine learning model can be effectively utilized to obtain accurate and reliable model prediction results in a short time, thereby improving efficiency and saving time, and helping to realize the automation of the multi-stage pressure regulation method for distributed energy pipeline natural gas transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is an exemplary platform structure diagram of an Internet of Things system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a multi-stage pressure regulation method for natural gas transmission in a distributed energy pipeline according to some embodiments of this specification;

[0011] Figure 3 is a schematic diagram of determining characteristic boost parameters according to some embodiments of this specification;

[0012] Figure 4 is a schematic diagram of a pressure consumption model according to some embodiments of the present specification;

[0013] Figure 5 It is a schematic diagram of determining linkage adjustment parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 It is an exemplary platform structure diagram of the Internet of Things system shown in some embodiments of this specification.

[0019] like Figure 1 As shown, in some embodiments, the Internet of Things system 100 includes an operation user platform 110, an operation service platform 120, a management platform 130, a sensor network platform 140 and a perception control platform 150 that interact in sequence.

[0020] The operation user platform 110 may be a platform for interacting with users. In some embodiments, the operation user platform 110 is configured as a terminal device, such as a mobile phone, a computer, and applications and web pages installed thereon.

[0021] In some embodiments, the operation user platform 110 and the operation service platform 120 exchange information.

[0022] The operation service platform 120 may be a platform for conveying user needs and control information. The operation service platform 120 may obtain information from the management platform 130 (e.g., database 132) and send it to the operation user platform 110. For example, the operation service platform 120 sends pressurization task information, pressurization parameters, transportation status data within the pipeline branch, pipeline environment data of the pipeline branch, etc. to the operation user platform 110. In some embodiments, the operation service platform 120 is configured as a server.

[0023] In some embodiments, the operation service platform 120 may exchange information with the management platform 130 .

[0024] The management platform 130 can be a platform that coordinates and coordinates the connections and collaborations between various functional platforms, gathers all the information of the Internet of Things, and provides perception management and control management functions for the Internet of Things operation system.

[0025] In some embodiments, the management platform 130 may include a processor 131 and a database 132. In some embodiments, the processor 131 and the database 132 exchange information. In some embodiments, the processor 131 may be used to process data related to the Internet of Things system 100. For example, the processor 131 may determine the basic boosting parameters of the target boosting station based on the station information of the target boosting station. In some embodiments, the database 132 may be used to store data and / or instructions related to the Internet of Things system 100. For example, the database 132 may store the station information of the target boosting station, downstream pipeline data, etc.

[0026] In some embodiments, the management platform 130 may respectively exchange information with the operation service platform 120 and the sensor network platform 140. For example, the management platform 130 may send a boost parameter to the operation service platform 120. For another example, the management platform 130 may send an instruction for obtaining current natural gas data and / or historical natural gas data to the sensor network platform 140 to obtain current natural gas data and / or historical natural gas data.

[0027] The sensor network platform 140 may be a functional platform for managing sensory communications. In some embodiments, the sensor network platform 140 may implement the functions of sensory communication of sensory information and sensory communication of control information, for example, to implement sensory communication of sensory information of current natural gas data and / or historical natural gas data. In some embodiments, the sensor network platform 140 may include a first sensor network sub-platform 141 related to a pressurizing device, a second sensor network sub-platform 142 related to an in-pipe monitoring device, and a third sensor network sub-platform 143 related to an environmental sensing device. Among them, the pressurizing device is a device for increasing the pressure of natural gas in a pipeline, the in-pipe monitoring device is a device for monitoring the state parameters (e.g., temperature, pressure, etc.) of natural gas in a pipeline, and the environmental sensing device is a device for monitoring the state parameters (e.g., temperature, humidity, etc.) of the environment surrounding the pipeline.

[0028] The perception control platform 150 may be a functional platform for generating perception information and executing control information. In some embodiments, the perception control platform 150 may include a first perception control sub-platform 151 related to the boosting device, a second perception control sub-platform 152 related to the in-pipe monitoring device, and a third perception control sub-platform 153 related to the environmental perception device.

[0029] In some embodiments, the sensing control platform 150 also includes a distributed in-pipeline monitoring device. For more information about the distributed in-pipeline monitoring device, see Figure 2 part.

[0030] In some embodiments, each sub-platform in the sensor network platform 140 can be configured as a gateway and a data interface to interact with each sub-platform in the perception control platform 150. For example, the first sensor network sub-platform 141 can exchange information with the first perception control sub-platform 151. For another example, the second sensor network sub-platform 142 exchanges information with the second perception control sub-platform 152. For another example, the third sensor network sub-platform 143 exchanges information with the third perception control sub-platform 153.

[0031] In some embodiments of this specification, based on the Internet of Things system 100, an information operation closed loop can be formed between the perception control platform 150 and the operation user platform 110, and coordinated and regularly operated under the unified management of the processor 131 of the management platform 130, thereby realizing the informatization and intelligence of natural gas transportation for users.

[0032] It should be noted that the above description of the multi-stage pressure regulation method and the Internet of Things system for distributed energy pipeline natural gas transmission is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The operation user platform 110, operation service platform 120, management platform 130, sensor network platform 140 and perception control platform 150 disclosed in the specification can be different platforms in one system, or one platform can realize the functions of two or more platforms mentioned above. For example, each platform can share a storage module, or each platform can have its own storage module. Such variations are all within the protection scope of this specification.

[0033] Figure 2 This is an exemplary flow chart of a multi-stage pressure regulation method for distributed energy pipeline natural gas transportation according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 may be executed by the management platform 130 (eg, the processor 131 configured in the management platform 130).

[0034] Step 210, obtain the site information of the target booster station and the downstream pipeline data of the target booster station from the database of the management platform, and obtain the boosting task information based on the distributed in-pipe monitoring equipment configured in the upstream pipeline branch in the perception control platform.

[0035] The target boosting station refers to the boosting station for which boosting parameters need to be determined.

[0036] In some embodiments, the management platform can determine the target boosting station in a variety of ways. For example, the management platform can determine a newly-commissioned boosting station as a target boosting station. For another example, when the change in the natural gas flow rate of the boosting station within a preset time is greater than a flow change threshold and / or the change in the natural gas input pressure is greater than an input pressure change threshold, the management platform can determine the boosting station as a target boosting station. The flow change threshold or the input pressure change threshold can be a preset value.

[0037] The station information may reflect the attribute characteristics of the target boosting station. In some embodiments, the station information may include the level of the target boosting station, the scale of the target boosting station, and the location and number of secondary boosting stations. A secondary boosting station refers to a downstream boosting station that is directly connected to the target boosting station through a pipeline branch.

[0038] The level of the boosting station can reflect the hierarchical structure of the boosting station in the natural gas transmission network. In some embodiments, the level of the boosting station is expressed as level zero, level one, level two, level three, etc. It can be understood that the secondary boosting station of the level two boosting station is a level three boosting station. The larger the level of the boosting station, the more the boosting station is located downstream of the natural gas transmission network. The greater the drop in gas pressure during the transmission of the natural gas in the pipeline, the more it needs to be pressurized; the smaller the level of the boosting station, the more the boosting station is located upstream of the natural gas transmission network. When the boosting station performs a boosting operation, the more downstream boosting stations are affected.

[0039] In some embodiments, the management platform may determine the level of the boosting station in a variety of ways. For example, a boosting station located on the natural gas main pipeline is determined as a zero-level boosting station, a boosting station directly connected to the zero-level boosting station through a pipeline branch is determined as a first-level boosting station, and a boosting station directly connected to the first-level boosting station through a pipeline branch is determined as a second-level boosting station, etc.

[0040] The scale of the boosting station may reflect the boosting capacity of the boosting station. In some embodiments, the scale of the boosting station may include the maximum natural gas flow rate of the boosting station, the number of boosting equipment, etc.

[0041] The upstream and downstream of the pipeline branch can reflect the direction of natural gas flow. Natural gas flows from upstream to downstream. In some embodiments, the natural gas transmission pipeline network may include several boosting stations and several pipeline branches. The pipeline that inputs natural gas to the boosting station is the upstream pipeline branch of the boosting station, and the pipeline that outputs natural gas from the boosting station is the downstream pipeline branch of the boosting station.

[0042] The pipeline data may reflect the relevant characteristics of the pipeline branch. In some embodiments, the pipeline data includes pipeline size, pipeline spatial position, pipeline branching situation, etc. Among them, the pipeline size may include the cross-sectional area of ​​the pipeline, and the pipeline spatial position may be represented in the form of a space vector, and the starting point and end point of the space vector are the position coordinates of the pipeline inlet and the pipeline outlet, respectively. The pipeline branching situation may include the number of downstream pipeline branches at the output end of the pipeline branch and the pipeline size of each downstream pipeline branch.

[0043] The downstream pipeline data is pipeline data of the downstream pipeline branch.

[0044] The downstream pipeline branch includes a collection of at least one pipeline segment from the target boosting station to the next downstream boosting station. A pipeline segment is a complete natural gas transmission pipeline for transporting natural gas. Through the interconnection of numerous pipeline segments, a huge natural gas transmission network can be formed.

[0045] In some embodiments, the number of downstream pipeline branches of the target boosting station is the same as the number of secondary boosting stations of the target boosting station. For example, when the target boosting station has N secondary boosting stations, the number of downstream pipeline branches of the target boosting station is also N.

[0046] In some embodiments, the station information of the boosting station and the pipeline data of the pipeline branch may be pre-stored in the database 132 , and the processor may directly obtain the station information of the boosting station and the downstream pipeline data of the downstream pipeline branch from the database 132 .

[0047] The distributed in-pipe monitoring device is a detection device for monitoring natural gas related parameters in a pipeline branch. The distributed in-pipe monitoring device is arranged inside the transmission pipeline. In some embodiments, the distributed in-pipe monitoring device includes multiple types of sensors. For example, a temperature sensor, a pressure sensor, a flow sensor, etc. The distributed in-pipe monitoring device is deployed in a pipeline branch.

[0048] In some embodiments, distributed in-pipe monitoring equipment is used to obtain pressurization task information.

[0049] The boosting task information may reflect the relevant parameters of the natural gas to be boosted entering the target boosting station. In some embodiments, the boosting task information may include the pressure, flow rate, flow rate, etc. of the natural gas to be boosted. The distributed in-pipe monitoring equipment includes a pressure sensor, a flow rate sensor, a flow sensor, etc.

[0050] In some embodiments, in order to save costs, the distributed in-pipe monitoring equipment can be deployed at key nodes of pipeline branches, such as welding points of pipeline branches, branch points of pipeline branches, etc.

[0051] In some embodiments, the distributed in-pipe monitoring device can also obtain transportation status data. The transportation status data can reflect the relevant parameters of the pressurized natural gas in the downstream pipeline branch of the target boosting station. In some embodiments, the transportation status data can include the pressure, flow rate, flow rate, etc. of the pressurized natural gas.

[0052] Step 220: Determine basic boosting parameters of the target boosting station based on the station information of the target boosting station.

[0053] The basic boosting parameters refer to the default boosting parameters of the boosting station. The basic boosting parameters may reflect the boosting parameters for boosting under normal circumstances. The normal situation may be that the natural gas consumption of the downstream pipeline branch is relatively stable. The normal situation may also be that the natural gas pressure of the downstream pipeline branch is constant. In some embodiments, the basic boosting parameters may include the basic natural gas pressure.

[0054] In some embodiments, the management platform can determine the basic boosting parameters of the target boosting station in a variety of ways. For example, the management platform can determine the basic boosting parameters of the target boosting station based on a first preset table. The management platform can construct a first preset table based on historical station information and historical basic boosting parameters. The first preset table contains the correspondence between different historical station information and different historical basic boosting parameters. The management platform can determine the basic boosting parameters of the current target boosting station by querying the first preset table based on the station information of the current target boosting station.

[0055] Step 230, determining characteristic boosting parameters of the target boosting station based on basic boosting parameters, downstream pipeline data, and boosting task information.

[0056] The characteristic boosting parameters refer to the boosting parameters that are personalized according to the specific conditions of the boosting station. In some embodiments, the management platform can increase or decrease the basic boosting parameters of the target boosting station to obtain the characteristic boosting parameters of the target boosting station.

[0057] In some embodiments, the management platform can construct a first characteristic vector based on the basic boosting parameters, downstream pipeline data and boosting task information of the target boosting station; perform vector matching in a first vector database based on the first characteristic vector to determine a first association vector; and determine the characteristic boosting parameters of the target boosting station based on the first association vector.

[0058] In some embodiments, there are multiple ways to construct the first feature vector, for example, the first feature vector can be constructed by using methods such as TF-IDF (Term Frequency-Inverse Document Frequency), One-Hot, Word2Vec, etc.

[0059] The first vector database may include multiple first reference vectors and corresponding reference characteristic boosting parameters. Each first reference vector may be constructed based on historical basic boosting parameters, historical downstream pipeline data, and historical boosting task information during normal operation of the boosting station. The first reference vector is constructed in a similar manner to the first characteristic vector. The reference characteristic boosting parameters may be actual characteristic boosting parameters corresponding to the first reference vector. The actual boosting parameters refer to historical boosting parameters that ultimately remain unchanged after the historical basic boosting parameters corresponding to the first reference vector have been repeatedly adjusted. What ultimately remains unchanged refers to historical boosting parameters that remain unchanged when the boosting task information is constant.

[0060] In some embodiments, the management platform may determine, through vector matching, a first reference vector that meets a first preset condition as the first association vector. The first preset condition may refer to a preset condition for determining the first association vector. In some embodiments, the first preset condition may include that the vector distance meets a distance threshold, that the vector distance is minimum, etc.

[0061] In some embodiments, the management platform may determine the characteristic supercharging parameters of the target supercharging station based on the supercharging effect of the reference characteristic supercharging parameters corresponding to the first correlation vector. For example, the management platform may select the reference characteristic supercharging parameters with the best supercharging effect as the characteristic supercharging parameters of the final target supercharging station.

[0062] The boosting effect can reflect the boosting effect of the characteristic boosting parameter. In some embodiments, the boosting effect can include the difference between the actual natural gas pressure of the downstream pipeline branch and the ideal natural gas pressure. The smaller the difference, the closer the actual natural gas pressure of the downstream pipeline branch is to the ideal natural gas pressure, and the better the boosting effect. The ideal natural gas pressure can be determined based on prior experience.

[0063] In some embodiments, the management platform can also determine the pressure consumption data of the downstream pipeline branch of the target boosting station based on the downstream pipeline data and the boosting task information; and determine the characteristic boosting parameters of the target boosting station based on the pressure consumption data of the downstream pipeline branch. For more information about this embodiment, please refer to Figure 3 and related instructions.

[0064] Step 240, a boosting instruction is generated based on the characteristic boosting parameters and sent to a target boosting station through the sensing control platform, so as to control the target boosting station to perform a boosting operation on the natural gas in the downstream pipeline branch.

[0065] The boosting instruction is an instruction for adjusting the operating state of the boosting station. In some embodiments, the boosting instruction includes the natural gas pressure increase range or the natural gas pressure decrease range of the target boosting station.

[0066] In some embodiments, the boosting instruction further includes a target natural gas pressure of the target boosting station.

[0067] In some embodiments, when the target boosting station receives the boosting instruction, it can control the boosting equipment (eg, natural gas compressor, etc.) inside the target boosting station to boost the natural gas input into the target boosting station.

[0068] Step 250, in response to the pressurization instruction being executed, obtaining the transportation status data of the natural gas in at least one pipeline branch in a preset area based on the distributed in-pipeline monitoring equipment.

[0069] In some embodiments, the management platform obtains the transportation status data of the natural gas in the downstream pipeline branch based on the distributed in-pipe monitoring equipment configured in the downstream pipeline branch. For more information about the distributed in-pipe monitoring equipment and transportation status data, please refer to the above.

[0070] Step 260 , in response to the transport status data not satisfying a preset condition, determining linkage adjustment parameters of the target boosting station and its associated boosting stations based on the transport status data.

[0071] The preset condition is a judgment condition for judging whether the transportation status data is qualified. In some embodiments, the preset condition may include: the natural gas pressure included in the transportation status data is within a preset pressure range, the natural gas flow is within a preset flow range, and the natural gas flow rate is within a preset flow rate range. The preset pressure range, the preset flow range, and the preset flow rate range can be set based on prior experience.

[0072] In some embodiments, different pipeline branches may correspond to different preset conditions, and the preset conditions of different pipeline branches may be determined based on the historical transportation status data of the pipeline branch. For example, for a section of a pipeline branch, the management platform may screen the historical transportation status data of the pipeline branch, and retain several groups of historical transportation status data in which no safety accidents (e.g., natural gas leaks, pipeline damage, etc.) have occurred as reference transportation status data. The management platform may count the historical pressure ranges, historical flow ranges, and historical flow rate ranges of several groups of reference transportation status data, and determine the statistically obtained historical pressure ranges, flow ranges, and flow rate ranges as the preset pressure ranges, preset flow ranges, and preset flow rate ranges corresponding to the pipeline branch.

[0073] In some embodiments, when one of the natural gas pressure, natural gas flow rate, and natural gas flow rate is not within the corresponding preset range, the transportation status data is deemed to not meet the preset condition. In other embodiments, when the natural gas pressure, natural gas flow rate, and natural gas flow rate are all not within the corresponding preset range, the transportation status data is deemed to not meet the preset condition. The preset range includes a preset pressure range, a preset flow range, and a preset flow rate range.

[0074] An associated boosting station is a boosting station whose boosting effect will be affected by the target boosting station. Since pipeline branches usually pass through multiple boosting stations, the characteristic boosting parameters of the target boosting station often affect the surrounding boosting stations.

[0075] In some embodiments, the associated boosting stations of the target boosting station may be determined by prior experience.

[0076] In some embodiments, the management platform may determine, as associated boosting stations of the target boosting station, the parallel boosting stations and downstream boosting stations corresponding to pipeline branches in the natural gas transmission pipeline network whose transport status data meets preset conditions, but whose transport status data does not meet the preset conditions after the target boosting station adopts characteristic boosting parameters.

[0077] A parallel boosting station refers to a boosting station that has the same upstream natural gas station as the target boosting station. The upstream natural gas station may include an upstream boosting station, an upstream gas distribution station, an upstream gas mixing station, etc. Among them, a gas distribution station is a natural gas station used to control the flow of natural gas and prevent the backflow of natural gas, and a gas mixing station is a natural gas station used to control the composition ratio of natural gas (for example, mixing natural gas from different sources, adding odorants to natural gas, etc.).

[0078] In some embodiments, the management platform determines the state fluctuation data of the associated pipeline branch based on the transportation state data of the associated pipeline branch of the target booster station; determines the associated influence degree of the associated pipeline branch based on the state fluctuation data of the associated pipeline branch; and determines the associated booster station based on the associated influence degree of the associated pipeline branch.

[0079] The state fluctuation data can reflect the fluctuation of data in the pipeline section. For example, the state fluctuation data can reflect the fluctuation of data such as the natural gas flow rate, natural gas flow rate, and natural gas pressure in the pipeline. In some embodiments, for a pipeline branch, the management platform can obtain the transportation state data before and after the target boosting station adopts the characteristic boosting parameters, and determine the difference between the two collected transportation state data as the state fluctuation data of the pipeline branch.

[0080] The association influence degree can reflect the degree to which the pipeline branch is affected by the target boosting station. In some embodiments, when the target boosting station adopts characteristic boosting parameters, the boosting stations corresponding to some pipeline branches that are less affected by the target boosting station do not need to adjust parameters. Therefore, the association influence degree can be used to determine whether the boosting station corresponding to the pipeline branch is an associated boosting station.

[0081] Based on the association influence of at least one pipeline branch, determining the associated boosting station can be achieved in a variety of ways. In some embodiments, when the absolute value of the association influence of at least one pipeline branch exceeds a preset association threshold, the management platform can determine the upstream boosting station of the pipeline branch as the associated boosting station. The preset association threshold can be preset based on prior experience.

[0082] In some embodiments, the management platform can obtain state fluctuation data in historical boost records without any safety accidents, and determine the statistical value (for example, maximum value, mean, median, etc.) of the state fluctuation data without any safety accidents as a preset association threshold.

[0083] In some embodiments of the present specification, associated boosting stations are determined based on the associated influence of pipeline branches, which can effectively avoid determining the boosting stations corresponding to pipeline branches that are less affected by the target boosting station as associated boosting stations, thereby avoiding the waste of computing power and time caused by blindly making large-scale linkage adjustments, and helping to improve the response speed and computing efficiency of the Internet of Things system for distributed energy pipeline natural gas transportation.

[0084] The linkage adjustment parameter is a parameter for synchronously adjusting the boosting parameters of the associated boosting station and the target boosting station. In some embodiments, the linkage adjustment parameter includes the natural gas pressure adjustment amplitude and adjustment direction of the associated boosting station and the target boosting station, such as an increase of 5% and a decrease of 10%.

[0085] In some embodiments, the management platform may determine the deviation relationship of the transportation status data, and determine the linkage adjustment parameters of the target boosting station or the associated boosting stations by querying the linkage adjustment rules.

[0086] The deviation relationship can reflect the magnitude of the deviation of the transport status data from the corresponding preset range. The deviation relationship can include the size relationship and distance between the transport status data and the upper or lower limit of the corresponding preset range. In some embodiments, when the transport status data is less than the lower limit of the corresponding preset range, the deviation relationship can be expressed as the difference between the distance of the transport status data and the lower limit of the preset range; when the transport status data is greater than the upper limit of the corresponding preset range, the deviation relationship can be expressed as the difference between the distance of the transport status data and the upper limit of the preset range. For example, when the natural gas pressure is 40 MPa and the preset pressure range is 50 MPa to 100 MPa, the deviation relationship is -10 MPa.

[0087] In some embodiments, the linkage adjustment rule includes a mapping relationship between a deviation relationship and a linkage adjustment parameter. For example, the deviation relationship includes that if the transport status data is 10% less than the lower limit of the preset range, the corresponding upstream boosting station's boosting parameter is increased by 10%.

[0088] In some embodiments, the management platform can determine the linkage adjustment rules based on the test results. For example, for a reference deviation relationship, the management platform can continuously fine-tune the linkage adjustment parameters adopted by the target booster station or the associated booster station, and monitor whether the transportation status data of the downstream pipeline branch meets the corresponding preset conditions. When the preset conditions are met, the management platform can use the reference deviation relationship and the corresponding fine-tuned linkage adjustment parameters as the test results. The management platform can determine the linkage adjustment rules based on the test results by function fitting, preset table construction, etc.

[0089] In some embodiments, for a downstream pipeline branch of a target booster station or an associated booster station, the management platform can determine the linkage adjustment sub-parameters of at least one pipeline segment by querying the linkage adjustment rules based on the deviation relationship of the transportation status data of at least one pipeline segment of the downstream pipeline branch. The management platform can determine the linkage adjustment parameters of the target booster station and its associated booster station for the downstream pipeline branch by weighted summation based on the linkage adjustment sub-parameters of at least one pipeline segment. Among them, the weight corresponding to the linkage adjustment sub-parameter of each pipeline segment can be positively correlated to the distance from the location on the pipeline segment where the transportation status data is collected to the upstream booster station or the downstream booster station, that is, the pipeline segments at both ends have a greater weight than the pipeline segment in the middle.

[0090] Step 270, generating a linkage adjustment instruction based on the linkage adjustment parameters and sending it to the perception control platform to update the characteristic boosting parameters of the target boosting station and its associated boosting stations.

[0091] The linkage adjustment instruction is an instruction for synchronously adjusting the characteristic boosting parameters of the target boosting station and its associated boosting stations. In some embodiments, the linkage adjustment instruction includes linkage adjustment parameters corresponding to the target boosting station and its associated boosting stations.

[0092] In some embodiments, the management platform adjusts the characteristic boosting parameters of the target boosting station and its associated boosting stations according to the natural gas pressure adjustment amplitude and adjustment direction included in the linkage adjustment parameters, thereby updating the characteristic boosting parameters of the target boosting station and its associated boosting stations.

[0093] In some embodiments of the present specification, by determining the characteristic boosting parameters of the target boosting station, it is helpful to achieve personalized adjustment of the boosting station, thereby ensuring that the gas pressure of the downstream pipeline branch of the boosting station meets actual demand; in response to the transportation status data not satisfying the preset conditions, the linkage adjustment parameters of the target boosting station and its associated boosting stations are determined based on the transportation status data, so that while adjusting the boosting parameters of the target boosting station, the potential impact of the natural gas pressure change of the target boosting station on the surrounding boosting stations can be taken into account and adaptive adjustments can be made, which helps to enhance the synergy between different boosting stations, thereby improving the boosting station management capabilities of the Internet of Things system and the parallel processing capabilities of adjusting multiple boosting stations at the same time.

[0094] Figure 3 It is a schematic diagram of determining characteristic boost parameters according to some embodiments of this specification.

[0095] In some embodiments, Figure 3As shown, the management platform determines the pressure consumption data 330 of the downstream pipeline branch of the target boosting station based on the downstream pipeline data 310 and the boosting task information 320; and determines the characteristic boosting parameters 340 of the target boosting station based on the pressure consumption data 330 of the downstream pipeline branch.

[0096] The pressure consumption data refers to the ratio of the pressure drop of natural gas when it passes through the pipeline branch. Due to the friction between natural gas and the pipe wall during transportation and the influence of devices such as valves, the pressure of natural gas at the pipeline outlet is usually lower than the pressure at the pipeline inlet. In some embodiments, the pressure consumption data can be expressed as the percentage of the natural gas pressure at the outlet of the downstream pipeline branch compared to the natural gas pressure at the inlet of the downstream pipeline branch.

[0097] In some embodiments, the management platform can determine the pressure consumption data in a variety of ways. For example, the management platform can perform similarity matching based on the current downstream pipeline data and boosting task information with the historical downstream pipeline data and historical boosting task information of the historical pressure regulation records, select multiple groups of historical pressure regulation records that meet the similarity matching conditions, and obtain the corresponding multiple groups of historical pressure consumption data. The management platform can determine the statistical values ​​(e.g., mean, median, etc.) of the multiple groups of historical pressure consumption data as the pressure consumption data.

[0098] In some embodiments, the management platform can also determine the pressure consumption data of the downstream pipeline branch through the pressure consumption model based on the boosting task information, the pipeline data sequence of the downstream pipeline branch, and the pipeline environment data sequence. For more information about this part, please refer to Figure 4 and its related contents.

[0099] In some embodiments, the management platform can obtain pipeline environmental data of at least one pipeline segment in real time based on an environmental sensing device; in response to a change rate of the pipeline environmental data exceeding an environmental change threshold, the pressure consumption data of the downstream pipeline branch is updated through a pressure consumption model, and the characteristic boosting parameters of the target boosting station are updated.

[0100] The environmental sensing device is a device used to collect pipeline environmental data. The environmental sensing device is arranged outside the delivery pipeline. In some embodiments, the environmental sensing device may include but is not limited to a temperature sensor, a humidity sensor, an air pressure sensor, etc. The management platform can obtain pipeline environmental data through environmental sensing devices distributed around the pipeline.

[0101] The pipeline environment data is data reflecting the property characteristics of the environment around the pipeline. In some embodiments, the pipeline environment data includes the temperature, humidity, air pressure, etc. of the environment around the pipeline segment.

[0102] The change rate of the pipeline environment data can reflect the degree of change of the pipeline environment data. In some embodiments, the change rate of the pipeline environment data can be expressed as the increase or decrease of the current pipeline environment data compared to the pipeline environment data at a preset time point. The preset time point can be one hour before the current time, one day before, etc.

[0103] The environmental change threshold is a judgment threshold used to judge whether the characteristic boost parameter needs to be updated.

[0104] In some embodiments, the environmental change threshold may be a system preset value or a manually preset value.

[0105] In some embodiments, the environmental change threshold of a pipeline section may be positively correlated with the natural gas pressure, natural gas flow rate, and natural gas flow rate of the pipeline section. For example, when the natural gas pressure, natural gas flow rate, and natural gas flow rate of the pipeline section are smaller, they are more susceptible to fluctuations in the pipeline's external environment. At this time, the environmental change threshold may be appropriately lowered, and timely adjusted before the relevant parameters of the natural gas in the pipeline section fluctuate.

[0106] In some embodiments, the management platform can construct a second feature vector based on the natural gas pressure, natural gas flow rate and natural gas flow rate of the current transportation status data; perform vector matching in the second vector database based on the second feature vector to determine a second association vector; and determine a historical environmental change threshold based on the second association vector. The method of constructing the second feature vector is similar to the method of constructing the first feature vector. For details, please refer to the method of constructing the second feature vector. Figure 2 The relevant content of constructing the first eigenvector in .

[0107] In some embodiments, the management platform can screen the historical transportation status data, retaining the historical transportation status data in which the historical natural gas pressure is always within the preset pressure range, the historical natural gas flow rate is always within the preset flow range, and the historical natural gas flow rate is always within the preset flow rate range as candidate transportation status data. For each candidate transportation status data, the management platform can determine the maximum and minimum values ​​of its pipeline environment data within a preset time period, and respectively calculate the change rate of the maximum and minimum values ​​of the pipeline environment data relative to the reference environment data, and select the larger change rate of the two as the reference environment change threshold corresponding to the candidate transportation status data. Among them, the reference environment data can be the pipeline environment data corresponding to the historical transportation status data of the natural gas pressure, natural gas flow rate, and natural gas flow rate that are closest to the intermediate values ​​of the preset pressure range, the preset flow range, and the preset flow rate range. The reference environment data can also be preset pipeline environment data.

[0108] The second vector database may include multiple second reference vectors and corresponding reference environment change thresholds. Each second reference vector may be constructed based on the historical natural gas pressure, historical natural gas flow, and historical natural gas flow rate of the candidate transportation state data. The second reference vector is constructed in a similar manner to the second feature vector. After the second vector database is constructed, it may be stored in a database of the management platform.

[0109] In some embodiments, the management platform may determine, through vector matching, a second reference vector that meets the second preset condition as the second association vector, and use the reference environment change threshold corresponding to the second association vector as the final environment change threshold. The second preset condition may refer to a preset condition for determining the second association vector. In some embodiments, the second preset condition may include that the vector distance meets the distance threshold, the vector distance is minimum, etc.

[0110] In some embodiments, in response to the change rate of the pipeline environment data exceeding the environment change threshold, the management platform can re-determine the pressure consumption data of the downstream pipeline branch through the pressure consumption model based on the pipeline data sequence and the updated pipeline environment data sequence, and update the characteristic boosting parameters of the target boosting station according to the re-determined pipeline environment data. For more information on determining the pressure consumption data of the downstream pipeline branch based on the pressure consumption model, see Figure 4 and its related description.

[0111] In some embodiments of the present specification, by using a second vector database to determine the environmental change threshold, the speed and accuracy of determining the environmental change threshold can be effectively improved; in response to when the change rate of pipeline environmental data exceeds the environmental change threshold, the pressure consumption data of the downstream pipeline branch is updated through the pressure consumption model, and the characteristic boosting parameters of the target boosting station are updated. When the environment around the pipeline changes significantly, timely adjustments can be made, which helps to improve the responsiveness of the Internet of Things system for distributed energy pipeline natural gas transportation to abnormal situations.

[0112] In some embodiments, the management platform may determine the characteristic boosting parameters of the target boosting station in a variety of ways based on the pressure consumption data of the downstream pipeline branch.

[0113] In some embodiments, the management platform can determine the adjustment parameters based on the pressure consumption data of the downstream pipeline branch; based on the adjustment parameters and the basic boosting parameters of the target boosting station, determine the characteristic boosting parameters of the target boosting station. The adjustment parameters include the proportion of the increase or decrease. The proportion of the increase or decrease can be the same as the proportion of the change in the pressure consumption data. For example, when the pressure consumption data of the target boosting station decreases by 5%, the increase in the characteristic boosting parameter 340 of the target boosting station can be 5% of the basic boosting parameter increase, that is, 105%*basic boosting parameter.

[0114] In some embodiments, the management platform may also determine theoretical boosting parameters of the downstream pipeline branch based on the pressure consumption data of the downstream pipeline branch; and determine characteristic boosting parameters of the target boosting station based on the theoretical boosting parameters of the downstream pipeline branch.

[0115] The theoretical boost parameter refers to the boost parameter that can ideally meet the gas supply demand of the downstream pipeline branch. The gas supply demand refers to the minimum natural gas pressure at which the natural gas users connected to the downstream pipeline branch can normally use the natural gas. In some embodiments, when the natural gas pressure in the downstream pipeline branch is too low, the downstream natural gas users may not be able to obtain sufficient natural gas, so the natural gas pressure of the downstream branch must at least meet the gas supply demand.

[0116] In some embodiments, the theoretical boost parameter is positively correlated to the ideal natural gas pressure of the downstream pipeline branch and the pressure consumption data of the downstream pipeline branch. For more information about the ideal natural gas pressure, see Figure 2 part.

[0117] For example, the theoretical boost parameter of the downstream pipeline branch can be obtained based on the following formula (1):

[0118] Wherein, L represents the theoretical boosting parameter of the downstream pipeline branch, Q represents the ideal natural gas pressure of the downstream boosting station of the downstream pipeline branch, and Y represents the pressure consumption data 330 of the downstream pipeline branch.

[0119] In some embodiments, the downstream pipeline branches include at least two, and the management platform can determine the theoretical boosting parameters of the at least two downstream pipeline branches of the target boosting station, and determine the statistical values ​​(e.g., mean, median, etc.) of the theoretical boosting parameters of the at least two downstream pipeline branches as the characteristic boosting parameters of the target boosting station. Different downstream pipeline branches of the target boosting station can be connected to different secondary boosting stations.

[0120] In some embodiments of the present specification, when the pressure consumption data of a downstream pipeline branch is large, the characteristic boost parameter can appropriately increase its characteristic boost parameter to ensure that the gas supply of the downstream pipeline branch is always sufficient. When the pressure consumption data of the downstream pipeline branch is small, the characteristic boost parameter can appropriately reduce its characteristic boost parameter to avoid leakage in the pipeline section due to excessive natural gas pressure in the downstream pipeline branch, thereby improving the accuracy and applicability of the characteristic boost parameter of the target boosting station.

[0121] In some embodiments, the downstream pipeline branches include at least two, and the management platform can determine the boosting weight of each of the at least two downstream pipeline branches based on the historical natural gas transportation volume of each of the at least two downstream pipeline branches; and determine the characteristic boosting parameters of the target boosting station based on the boosting weight and theoretical boosting parameters of each of the at least two downstream pipeline branches.

[0122] The boosting weight may reflect the influence of different downstream pipeline branches on determining the characteristic boosting parameter. The sum of the boosting weights of at least two downstream pipeline branches of the target boosting station may be 1.

[0123] In some embodiments, the boosting weight of the downstream pipeline branch may be positively correlated to the historical natural gas transportation volume of the downstream pipeline branch. For example, the larger the historical natural gas transportation volume of the downstream pipeline branch, the more natural gas users will be affected when the downstream pipeline branch is abnormal, and the greater the loss caused. Therefore, when determining the characteristic boosting parameters of the target boosting station, the larger the historical natural gas transportation volume of the downstream pipeline branch, the higher the corresponding boosting weight.

[0124] In some embodiments, the management platform may determine the theoretical supercharging parameter of at least one downstream pipeline branch of the target supercharging station, perform weighted summation of the theoretical supercharging parameters of all downstream pipeline branches according to corresponding supercharging weights, and determine the obtained result as the characteristic supercharging parameter of the target supercharging station.

[0125] In some embodiments of the present specification, the characteristic boosting parameters of the target boosting station are determined based on the boosting weight and theoretical boosting parameters of at least one downstream pipeline branch. This can take into account the different natural gas flow rates of the downstream pipeline branches, more accurately reflect the actual contributions of different downstream pipeline branches to the characteristic boosting parameters, and comprehensively consider the situation when the target boosting station has multiple downstream branches, which helps to improve the scope of application of the Internet of Things system for distributed energy pipeline natural gas transportation.

[0126] Figure 4 is a schematic diagram of a pressure consumption model according to some embodiments of the present specification.

[0127] In some embodiments, Figure 4 As shown, the management platform can obtain the pipeline data sequence 410 of the downstream pipeline branch from the database 132 of the management platform, and obtain the pipeline environment data sequence 420 of the downstream pipeline branch in a preset time period based on the environmental perception device configured in the perception control platform; based on the boosting task information 320, the pipeline data sequence 410 and the pipeline environment data sequence 420, the pressure consumption data 330 of the downstream pipeline branch is determined through the pressure consumption model 450.

[0128] The pipeline data sequence refers to a sequence obtained by sorting the pipeline data of at least one pipeline segment in the downstream pipeline branch. In some embodiments, the sorting method may be: sorting the pipeline segments in the downstream pipeline branch in the order from the target boosting station to the downstream boosting station. For more information about pipeline data, see Figure 2 .

[0129] The pipeline environment data sequence refers to a sequence obtained by sorting the pipeline environment data of at least one pipeline segment in the downstream pipeline branch. The sorting method of the pipeline environment data sequence can be the same as the sorting method of the pipeline data sequence. The pipeline environment data can reflect the characteristics of the surrounding environment of the pipeline segment. For more information about pipeline environment data, please refer to Figure 2 .

[0130] The preset time period is a time range for collecting pipeline data sequences and pipeline environment data sequences. In some embodiments, the preset time period can be preset based on prior experience, such as the past week, the past day, etc.

[0131] The pressure consumption model is a model for predicting the pressure consumption data of downstream pipeline branches. In some embodiments, the linkage boost model can be a machine learning model, such as a recurrent neural network (RNN) model or any combination of other custom model structures.

[0132] In some embodiments, Figure 4 As shown, the pressure consumption model 450 input may include the pipeline data sequence 410 , the pipeline environment data sequence 420 , and the pressurization task information 320 , and the output may include the pressure consumption data 330 of the downstream pipeline branch.

[0133] In some embodiments, Figure 4 As shown, the input of the pressure consumption model 450 also includes the state fluctuation data 430 of the downstream pipeline branch and the cleanliness 440 of the downstream pipeline branch.

[0134] The state fluctuation data can reflect the fluctuation of the flow rate, flow rate, pressure and other data of the natural gas in the downstream pipeline branch. For more information about the state fluctuation data, please refer to Figure 5 and related instructions.

[0135] Cleanliness can reflect the cleanliness of the downstream pipeline branches.

[0136] In some embodiments, the management platform can determine the cleanliness of the downstream pipeline branch based on the amount of impurities accumulated in the downstream pipeline branch. For example, the more impurities accumulated, the lower the cleanliness. The correspondence between different impurity accumulations and different cleanliness can be preset based on prior knowledge or historical data.

[0137] The impurity accumulation amount can reflect the amount of impurities accumulated and attached to the inner wall of the pipe section of the downstream pipe branch. In some embodiments, the impurity accumulation amount can be expressed as the weight of impurities attached to the inner wall per unit area.

[0138] In some embodiments, Figure 4 As shown, the management platform can obtain the cleaning record 444 and the natural gas transportation volume 443 of the downstream pipeline branch from the database of the management platform, and determine the impurity accumulation rate 442 of the downstream pipeline branch based on the cleaning record 444 and the natural gas transportation volume 443; determine the cleanliness 440 of the downstream pipeline branch based on the impurity accumulation rate 442 and the natural gas transportation volume of the downstream pipeline branch in the period from the current moment to the last pipeline branch cleaning.

[0139] The impurity accumulation rate is the amount of impurities accumulated when the downstream pipeline branch transports a unit weight of natural gas. In some embodiments, the management platform can obtain the amount of impurities accumulated and the natural gas transportation volume increased in a preset time period based on the cleaning records and natural gas transportation volume of the downstream pipeline branch, and further calculate the impurity accumulation rate in the preset time period. The preset time period is a historical time period, and the breakpoint of the preset time period can be the time point of the cleaning record.

[0140] In some embodiments, the management platform can determine the cleanliness of the downstream pipeline branch in a variety of ways based on the impurity accumulation rate and the natural gas transportation volume of the downstream pipeline branch in the period from the current moment to the last pipeline branch cleaning. For example, the management platform can multiply the natural gas transportation volume in the period from the current moment to the last pipeline branch cleaning by the impurity accumulation rate to obtain the impurity accumulation amount of the downstream pipeline branch at the current moment, and then determine the cleanliness of the downstream pipeline branch at the current moment.

[0141] In some embodiments of the present specification, by using state fluctuation data and the cleanliness of downstream pipeline branches as inputs of the pressure change model, the data dimension of the pressure change model can be broadened, which helps to improve the generalization ability and prediction accuracy of the model.

[0142] In some embodiments, the pressure consumption model can be obtained by training based on a large number of first training samples with first labels. The management platform can perform the following training process to obtain the pressure consumption model. The training process includes: obtaining multiple first training samples with first labels to form a first training sample set, and performing multiple rounds of iterations based on the first training sample set. Among them, at least one round of iteration includes: selecting one or more first training samples from the first training data set, inputting one or more first training samples into the initial pressure consumption model, and obtaining the model prediction output corresponding to one or more first training samples; substituting the model prediction output corresponding to one or more first training samples and the first labels corresponding to one or more first training samples into the formula of a predefined loss function to calculate the value of the loss function; according to the value of the loss function, iteratively updating the model parameters in the initial pressure consumption model until the iteration end condition is met, and the iteration is terminated to obtain the trained pressure consumption model. Among them, the iterative update of the model parameters of the initial pressure consumption model can be performed by a variety of methods, for example, it can be updated based on the gradient descent method. The iteration end condition may include the convergence of the loss function or the number of iterations reaching the iteration number threshold.

[0143] In some embodiments, the first training sample may include sample pressurization task information, a sample pipeline data sequence and a sample pipeline environment data sequence of a sample downstream pipeline branch, and the sample pressurization task information.

[0144] In some embodiments, the first label may be sample pressure consumption data corresponding to the first training sample. In some embodiments, the first training sample and the first label may be obtained based on historical data. For example, the management platform may use the historical boosting task information, the historical pipeline environment data sequence, and the historical pipeline data sequence in the historical boosting record as the first training sample, and calculate the historical pressure consumption data based on the historical pressure at the outlet of the target boosting station and the historical pressure at the inlet of the secondary boosting station as the first label. For more information about the secondary boosting station, please refer to Figure 2 part.

[0145] In some embodiments, the first training sample may further include sample state fluctuation data and sample cleanliness. For example, the management platform may use historical state fluctuation data and historical cleanliness in historical boost records as sample state fluctuation data and sample cleanliness.

[0146] In some embodiments of the present specification, by using a pressure consumption model to determine the pressure consumption data of a downstream pipeline branch, the data analysis and computing capabilities of a machine learning model can be effectively utilized to obtain accurate and reliable model prediction results in a short time, thereby improving efficiency and saving time, and helping to realize the automation of a multi-stage pressure regulation method for distributed energy pipeline natural gas transportation.

[0147] Figure 5 It is a schematic diagram of determining linkage adjustment parameters according to some embodiments of this specification.

[0148] In some embodiments, Figure 5 As shown, the management platform can determine the state fluctuation data 430 of the associated pipeline branch based on the transport state data 501 of the associated pipeline branch of the target boosting station; determine the boosting map 520 based on the state fluctuation data 430, the first related parameter 510 of the target boosting station and the second related parameter 511 of the associated boosting station; and process the boosting map 520 through the linkage boosting model 530 to determine the linkage adjustment parameter 540.

[0149] In some embodiments, the first related parameters of the target boosting station include the location of the target boosting station, the natural gas flow rate, characteristic boosting parameters, a pipeline data sequence, and a pipeline environment data sequence.

[0150] In some embodiments, the second related parameters associated with the boosting station include a location, a natural gas flow rate, and a characteristic boosting parameter of the associated boosting station.

[0151] For more information on the association of booster stations, transport status data, status fluctuation data, pipeline data series, and pipeline environmental data series, see Figure 2 and its related description.

[0152] The boosting graph refers to a knowledge graph that represents pipeline branches and boosting stations. The knowledge graph is a data structure composed of nodes and edges. Edges connect nodes, and nodes and edges can have attributes. The boosting graph can reflect the relationship between the target boosting station and the associated boosting stations connected through pipeline branches.

[0153] The boosting map may be composed of at least one node and at least one edge. In some embodiments, the nodes of the boosting map include a target boosting station node and an associated boosting station node. The node attributes of the target boosting station node and the associated boosting station node may include the location coordinates of the boosting station, the natural gas flow rate, and the characteristic boosting parameters. For more information about the natural gas flow rate and the characteristic boosting parameters, please refer to Figure 2 Related instructions.

[0154] In some embodiments, the edge corresponds to a pipeline branch between nodes, and the attributes of the edge include a pipeline data sequence, state fluctuation data, a pipeline environment data sequence, and an associated influence degree of the pipeline branch.

[0155] The distance between two nodes in the boosting graph can reflect the path distance between the boosting stations corresponding to the two nodes. When there is a pipeline branch connecting two nodes, the nodes are connected by an edge.

[0156] Just as an example, Figure 5As shown, in the boosting graph, the associated boosting station nodes include an upstream associated boosting station node 522 located upstream of the target boosting station node 521, and a downstream associated boosting station node 523 located downstream of the target boosting station node 521. When the target boosting station has two secondary boosting stations, two edges are used to connect the target boosting station node 521 with the two downstream associated boosting station nodes 523 corresponding to the two secondary boosting stations, respectively. The length of the edge is positively correlated to the path distance from the target boosting station to the secondary boosting station, and the direction of the edge can reflect the flow direction of the natural gas. The associated boosting station corresponds to the associated boosting station node in the boosting graph.

[0157] The linkage boost model is a prediction model for predicting linkage adjustment parameters. In some embodiments, the linkage boost model can be a machine learning model. For example, any one or combination of a graph neural network (GNN) model or other custom model structures.

[0158] In some embodiments, Figure 5 As shown, the input of the linkage boost model 530 may include a boost map 520 , and the output may include linkage adjustment parameters 540 corresponding to different nodes.

[0159] In some embodiments, the linkage boost model can be obtained by training based on a large number of second training samples with second labels. The management platform can perform the following training process to obtain the linkage boost model. The training process includes: obtaining multiple second training samples with second labels to form a second training sample set, and performing multiple rounds of iterations based on the second training sample set. Among them, at least one round of iteration includes: selecting one or more second training samples from the second training data set, inputting one or more second training samples into the initial linkage boost model, and obtaining the model prediction output corresponding to one or more second training samples; substituting the model prediction output corresponding to one or more second training samples and the second labels corresponding to one or more second training samples into the formula of a predefined loss function to calculate the value of the loss function; according to the value of the loss function, iteratively updating the model parameters in the initial linkage boost model until the iteration end condition is met, and the iteration is terminated to obtain the trained linkage boost model. Among them, the iterative update of the model parameters of the initial linkage boost model can be performed by a variety of methods, for example, it can be updated based on the gradient descent method. The iteration end condition may include the convergence of the loss function or the number of iterations reaching the iteration number threshold.

[0160] In some embodiments, the second training sample may include a sample boosting map. The second label may include sample linkage adjustment parameters corresponding to different nodes.

[0161] In some embodiments, the second training sample and the second label can be obtained based on historical data. For example, the management platform can obtain the location coordinates, historical natural gas flow, historical characteristic boosting parameters of the historical target boosting station and the historical associated boosting station from the database 132 of the management platform, as well as the historical pipeline data, historical state fluctuation data, historical pipeline environment data, and historical associated influence data of the historical downstream pipeline branches and the historical associated pipeline branches, and construct the historical boosting map as the second training sample, and use the historical linkage adjustment parameters of the historical target boosting station and the historical associated boosting station as the second label.

[0162] In some embodiments, after the target booster station and the associated booster stations execute the linkage adjustment parameters 540, since the pipeline data has changed, the original associated booster stations may meet the preset conditions, resulting in a decrease in the number of associated booster stations. At the same time, it may also cause more booster stations to be converted into associated booster stations, resulting in a change in the number of associated booster stations.

[0163] In some embodiments, in response to the increase in the number of associated boosting stations after executing the linkage adjustment parameters, the management platform can retrieve and obtain target training data in the second training sample set based on the associated characteristics of the target boosting station and the associated boosting stations; and perform scenario-based training on the linkage boosting model based on the target training data and the corresponding second label.

[0164] The association feature may reflect the degree of mutual influence between the target boosting station and the associated boosting station. In some embodiments, the association feature may include the total length of the pipeline branches between the target boosting station and the associated boosting station, the proximity, and the association influence of the pipeline branches. The proximity may reflect the number of boosting stations that need to be passed when the target boosting station leads to the associated boosting station in the shortest path. For example, a proximity of 1 indicates that there is one boosting station between the target boosting station and the associated boosting station.

[0165] In some embodiments, the management platform may search for training data in the training data set based on the association features between the target boosting station and the associated boosting stations, and determine the retrieved training data as the target training data.

[0166] For example, the management platform can determine the historical correlation features between the historical target booster station and the historical associated booster station in different training data, and use the correlation features between the current target booster station and the associated booster station as the correlation features to be matched. The management platform determines the training data corresponding to the historical correlation features whose similarity meets the preset similarity conditions as the target training data through similarity matching. Among them, the similarity matching algorithm may include but is not limited to the Manhattan distance method, the SVM method, etc. The preset similarity condition may be that the similarity is greater than the preset similarity threshold, etc.

[0167] In some embodiments, the management platform performs scenario-based training on the linkage boost model 530 based on the target training data to obtain a scenario-based boost model.

[0168] Scenario-based training refers to intensive training of the trained linkage supercharging model 530. In some embodiments, scenario-based training includes personalized training for the current associated supercharging station scenario. Scenario-based training is the same as the training method for training the linkage supercharging model, the difference being that scenario-based training is further intensive training based on the previously trained linkage supercharging model. For the specific process of scenario-based training of the linkage supercharging model 530, refer to the aforementioned description of the training of the linkage supercharging model 530.

[0169] In some embodiments, after executing the linkage adjustment parameter 540, the adjustment effect may be poor, resulting in an increase in the number of supercharging stations affected by the target supercharging station, that is, an increase in the number of associated supercharging stations. By performing scenario-based training on the linkage supercharging model 530 to obtain a scenario-based supercharging model, it is helpful to improve the applicability and calculation accuracy of the linkage supercharging model 530 for the current scenario, thereby ensuring the prediction effect of the linkage supercharging model 530.

[0170] In some embodiments of the present specification, by using the boosting map 520 to analyze and process the location coordinates of the boosting station, the natural gas flow rate, the characteristic boosting parameters 340, etc., it is possible to effectively mine the potential correlation between different information in the chaotic and complex data.

[0171] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0172] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0173] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0174] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0175] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0176] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0177] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A multi-stage pressure regulation method for natural gas transportation in a distributed energy pipeline, characterized in that: The method is performed based on a management platform of an Internet of Things system, wherein the Internet of Things system includes an operation user platform, an operation service platform, a management platform, a sensor network platform, and a perception control platform that interact in sequence, and the method includes: Obtaining the site information of the target boosting station and the downstream pipeline data of the target boosting station from the database of the management platform, and obtaining the boosting task information based on the distributed in-pipe monitoring equipment configured in the upstream pipeline branch in the perception control platform; Determining basic supercharging parameters of the target supercharging station based on the station information of the target supercharging station; Determining characteristic boosting parameters of the target boosting station based on the basic boosting parameters, the downstream pipeline data, and the boosting task information; Generate a boosting instruction based on the characteristic boosting parameter and send it to the target boosting station through the perception control platform, so as to control the target boosting station to perform a boosting operation on the natural gas in the downstream pipeline branch; In response to the boost instruction being executed, obtaining, based on the distributed in-pipeline monitoring equipment, transportation status data of natural gas in at least one pipeline branch in a preset area; In response to the transport status data not satisfying a preset condition, determining linkage adjustment parameters of the target boosting station and its associated boosting stations based on the transport status data; A linkage adjustment instruction is generated based on the linkage adjustment parameter and sent to the perception control platform to update the characteristic boosting parameters of the target boosting station and its associated boosting stations.

2. The method according to claim 1, characterized in that: The determining of the characteristic boosting parameters of the target boosting station based on the basic boosting parameters, the downstream pipeline data, and the boosting task information includes: Determine pressure consumption data of a downstream pipeline branch of the target boosting station based on the downstream pipeline data and the boosting task information; The characteristic boosting parameter of the target boosting station is determined based on the pressure consumption data of the downstream pipeline branch.

3. The method according to claim 2, characterized in that The determining, based on the downstream pipeline data and the boosting task information, the pressure consumption data of the downstream pipeline branch of the target boosting station comprises: Acquire a pipeline data sequence of the downstream pipeline branch from the database of the management platform; the downstream pipeline branch includes at least one pipeline segment, and the pipeline data sequence includes pipeline data of the at least one pipeline segment; Acquire a pipeline environment data sequence of the downstream pipeline branch in a preset period based on an environment perception device configured in the perception control platform, wherein the pipeline environment data sequence includes pipeline environment data of the at least one pipeline segment; Based on the boosting task information, the pipeline data sequence and the pipeline environment data sequence, the pressure consumption data of the downstream pipeline branch is determined by a pressure consumption model, and the pressure consumption model is a machine learning model.

4. The method according to claim 3, characterized in that The input of the pressure consumption model also includes the state fluctuation data of the downstream pipeline branch and the cleanliness of the downstream pipeline branch; The cleanliness of the downstream pipeline branch is determined by: Acquire the cleaning record and natural gas transportation volume of the downstream pipeline branch from the database of the management platform, and determine the impurity accumulation rate of the downstream pipeline branch based on the cleaning record and the natural gas transportation volume; The cleanliness of the downstream pipeline branch is determined based on the impurity accumulation rate and the natural gas transportation volume of the downstream pipeline branch from the current moment to the last pipeline branch cleaning.

5. The method according to claim 3, characterized in that: The method further comprises: Acquiring pipeline environmental data of the at least one pipeline segment in real time based on the environmental sensing device; In response to a change rate of the pipeline environment data exceeding an environment change threshold, the pressure consumption data of the downstream pipeline branch is updated through the pressure consumption model, and the characteristic boosting parameter of the target boosting station is updated.

6. The method according to claim 2, characterized in that The determining the characteristic boosting parameter of the target boosting station based on the pressure consumption data of the downstream pipeline branch comprises: Determining a theoretical pressurization parameter of the downstream pipeline branch based on the pressure consumption data of the downstream pipeline branch; The characteristic boosting parameter of the target boosting station is determined based on the theoretical boosting parameter of the downstream pipeline branch.

7. The method according to claim 6, characterized in that The downstream pipeline branches include at least two, and the determining the characteristic supercharging parameter of the target supercharging station based on the theoretical supercharging parameter of the downstream pipeline branches includes: Determining a pressure increase weight for each of at least two of the downstream pipeline branches based on a historical natural gas transportation volume for each of the at least two downstream pipeline branches; The characteristic boosting parameter of the target boosting station is determined based on the boosting weights of the at least two downstream pipeline branches and the theoretical boosting parameter.

8. The method according to claim 1, characterized in that: The method for determining the associated booster station includes: Determining state fluctuation data of the associated pipeline branch based on the transport state data of the associated pipeline branch of the target boosting station; Determining the association influence degree of the associated pipeline branch based on the state fluctuation data of the associated pipeline branch; The associated boosting station is determined based on the associated influence degree of the associated pipeline branch.

9. The method according to claim 1, characterized in that: The step of determining the linkage adjustment parameters of the target boosting station and its associated boosting stations based on the transport status data includes: Determining state fluctuation data of the associated pipeline branch based on the transport state data of the associated pipeline branch of the target boosting station; Determine a boosting map based on the state fluctuation data of the associated pipeline branch, a first related parameter of the target boosting station, and a second related parameter of the associated boosting station, wherein the first related parameter includes the location of the target boosting station, the natural gas flow rate, the characteristic boosting parameter, the pipeline data sequence, and the pipeline environment data sequence, and the second related parameter includes the location of the associated boosting station, the natural gas flow rate, and the characteristic boosting parameter; The boost map is processed by a linkage boost model to determine the linkage adjustment parameter, and the linkage boost model is a machine learning model.

10. An Internet of Things system for distributed energy pipeline natural gas transportation, characterized in that: The system includes an operation user platform, an operation service platform, a management platform, a sensor network platform and a perception control platform that interact in sequence; The management platform is configured as follows: Obtaining the site information of the target boosting station and the downstream pipeline data of the downstream pipeline branch of the target boosting station from the database of the management platform, and obtaining the boosting task information based on the distributed in-pipe monitoring equipment configured in the upstream pipeline branch in the perception control platform; Determining basic supercharging parameters of the target supercharging station based on the station information of the target supercharging station; Determining characteristic boosting parameters of the target boosting station based on the basic boosting parameters, the downstream pipeline data, and the boosting task information; Generate a boosting instruction based on the characteristic boosting parameter and send it to the target boosting station through the perception control platform, so as to control the target boosting station to perform a boosting operation on the natural gas in the downstream pipeline branch; In response to the boost instruction being executed, obtaining, based on the distributed in-pipeline monitoring equipment, transportation status data of natural gas in at least one pipeline branch in a preset area; In response to the transport status data not satisfying a preset condition, determining linkage adjustment parameters of the target boosting station and its associated boosting stations based on the transport status data; A linkage adjustment instruction is generated based on the linkage adjustment parameter and sent to the perception control platform to update the characteristic boosting parameters of the target boosting station and its associated boosting stations.

Images